Jack Parker-Holder
@jparkerholder
Followers
5K
Following
7K
Media
41
Statuses
984
Research Scientist @GoogleDeepMind & Honorary Lecturer @UCL_DARK interested in generating worlds from video data. Dad (๐ถ๐ถ), CFC fan, BJJ. Views are my own :)
London, England
Joined October 2018
Introducing ๐งGenie 2 ๐ง - our most capable large-scale foundation world model, which can generate a diverse array of consistent worlds, playable for up to a minute. We believe Genie 2 could unlock the next wave of capabilities for embodied agents ๐ง .
284
477
3K
RT @HedayatianSaeed: 1/8.In my first PhD paper, we tackled a major bottleneck in Quality-Diversity (QD) optimization for sequential decisioโฆ.
0
34
0
Super excited to have you back ๐บ๐ซถ๐.
Bit of an update! Iโve just wrapped up an incredible chapter at Runway โ huge thanks to the brilliant, supportive team for everything Iโve learned. And excited to share Iโll be heading back to @_rocktโs team at GDM next week! Canโt wait to work with such an amazing group again๐ซถ.
0
0
13
Excited to talk about world models @CVPR ๐.
๐ฌ#CVPR2025 ๐๐ฎ๐ญ๐จ๐ซ๐ข๐๐ฅ.๐บ๏ธ๐ญ๐๐๐ ๐ฝ๐๐
๐๐ ๐ฎ๐๐๐๐๐๐๐๐๐ ๐๐ ๐พ๐๐๐๐
๐ด๐๐
๐๐ @CVPR. ๐ ๐
June 11.๐Hosted by @MMLabNTU x @Kling_ai .๐ง Incredible lineup of speakers: @jparkerholder @Koven_Yu @baaadas @wanfufeng @akanazawa @sherryyangML
1
5
40
RT @_rockt: My @iclr_conf 2025 Keynote on "Open-Endedness, World Models, and the Automation of Innovation" is now publicly available:ย httpsโฆ.
0
39
0
RT @gbarthmaron: Not only is Veo 3 SoTA at t2v, t2va, and i2v, it can also generate speech in other languages too.
0
3
0
RT @ArtificialAnlys: Veo 3 debuts on the Artificial Analysis Video Arena Leaderboard in first place, with a significant lead over Googleโsโฆ.
0
67
0
Ps I didnโt work on it but Veo3 is mind blowing ๐.
0
0
7
I donโt really like to post โhot takesโ but itโs quite sad to see many people dunking on each otherโs work. Weโre all working hard, doing amazing things that wouldโve been impossible a few years ago. Thereโs plenty of success to go round, letโs stop throwing toys out of the pram!.
4
4
82
RT @doomie: 1/ Veo 3 launched today! An extraordinary feat from the team to put all the pieces together to create our SOTA audio-video geneโฆ.
0
16
0
RT @shlomifruchter: Once you turn on sound, you can't turn it off again. Excited to introduce our latest model, Veo 3, that can generate vโฆ.
0
16
0
Congrats (again) to the Veo team for pushing the frontier of whatโs possible! ๐.
Say goodbye to the silent era of video generation: Introducing Veo 3 โ with native audio generation. ๐ฃ๏ธ. Quality is up from Veo 2, and now you can add dialogue between characters, sound effects and background noise. Veo 3 is available now in the @GeminiApp for Google AI Ultra
0
2
79
RT @GoogleDeepMind: Video, meet audio. ๐ฅ๐ค๐. With Veo 3, our new state-of-the-art generative video model, you can add soundtracks to clips yโฆ.
0
1K
0
RT @MichaelD1729: Anyone else finding the NeurIPS reviewer biding impossible this year?. The affinity score is a poor proxy for my abilityโฆ.
0
5
0
World models could lead to a significant leap for open-ended learning and embodied AGI. Multiplayer brings another dimension. Great work!!.
Introducing Multiverse: the first AI-generated multiplayer game. Multiplayer was the missing piece in AI-generated worlds โ now itโs here. Players can interact and shape a shared AI-simulated world, in real-time. Training and research cost < $1.5K. Run it on your own PC. We
2
6
52
RT @PaglieriDavide: Gemini 2.5 Pro completes Pokรฉmon Blue ๐คฏ๐ฅ. But how does it fare in much harder, more unforgiving games?. On NetHack, itโฆ.
0
4
0